Tootfinder

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
Haokun Lin, Haobo Xu, Yichen Wu, Ziyu Guo, Renrui Zhang, Zhichao Lu, Ying Wei, Qingfu Zhang, Zhenan Sun
https://arxiv.org/abs/2508.14896

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
Recent advances in diffusion large language models (dLLMs) have introduced a promising alternative to autoregressive (AR) LLMs for natural language generation tasks, leveraging full attention and denoising-based decoding strategies. However, the deployment of these models on edge devices remains challenging due to their massive parameter scale and high resource demands. While post-training quantization (PTQ) has emerged as a widely adopted technique for compressing AR LLMs, its applicability to…

Making Pose Representations More Expressive and Disentangled via Residual Vector Quantization
Sukhyun Jeong, Hong-Gi Shin, Yong-Hoon Choi
https://arxiv.org/abs/2508.14561 https:…

Making Pose Representations More Expressive and Disentangled via Residual Vector Quantization
Recent progress in text-to-motion has advanced both 3D human motion generation and text-based motion control. Controllable motion generation (CoMo), which enables intuitive control, typically relies on pose code representations, but discrete pose codes alone cannot capture fine-grained motion details, limiting expressiveness. To overcome this, we propose a method that augments pose code-based latent representations with continuous motion features using residual vector quantization (RVQ). This d…

GDNSQ: Gradual Differentiable Noise Scale Quantization for Low-bit Neural Networks
Sergey Salishev, Ian Akhremchik
https://arxiv.org/abs/2508.14004 https://

GDNSQ: Gradual Differentiable Noise Scale Quantization for Low-bit Neural Networks
Quantized neural networks can be viewed as a chain of noisy channels, where rounding in each layer reduces capacity as bit-width shrinks; the floating-point (FP) checkpoint sets the maximum input rate. We track capacity dynamics as the average bit-width decreases and identify resulting quantization bottlenecks by casting fine-tuning as a smooth, constrained optimization problem. Our approach employs a fully differentiable Straight-Through Estimator (STE) with learnable bit-width, noise scale an…

Infrared Extended Uncertainty Principle Corrections and Quintessence-Induced Topology of Reissner-Nordstr\"om AdS Black Holes
Y. Sekhmani, G. G. Luciano, S. N. Gashti, A. Baruah
https://arxiv.org/abs/2508.14953

Infrared Extended Uncertainty Principle Corrections and Quintessence-Induced Topology of Reissner-Nordström AdS Black Holes
We present a unified topological and geometric analysis of charged Anti-de Sitter (AdS) black holes immersed in a quintessence field, incorporating infrared gravitational corrections arising from the Extended Uncertainty Principle (EUP). The latter modifies the standard Heisenberg uncertainty relation by introducing a minimal momentum/maximal length scale, which effectively captures long-wavelength quantum gravitational effects relevant to black hole thermodynamics in curved spacetimes. We deri…

Seven Sphere Quantization
Subhobrata Chatterjee, Can G\"ormez, Andrew Waldron
https://arxiv.org/abs/2507.14363 https://arxiv.org…

Seven Sphere Quantization
Co-oriented contact manifolds quite generally describe classical dynamical systems. Quantization is achieved by suitably associating a Schrödinger equation to every path in the contact manifold. We quantize the standard contact seven sphere by treating it as a homogeneous space of the quaternionic unitary group in order to construct a contact analog of Fedosov's formal connection on symplectic spinor bundles. We show that requiring convergence of the formal connection naturally filters the sym…

Ab-initio exploration of Gd monolayer interfaced with WSe$_2$: from electronic and magnetic properties to the anomalous Hall effect
Lyes Mesbahi (Laboratoire de Physique et Chimie Quantique), Omar Messaoudi (Laboratoire de Physique et Chimie Quantique), Hamid Bouzar (Laboratoire de Physique et Chimie Quantique), Samir Lounis (Institute of Physics, Martin-Luther-University Halle-Wittenberg, 06099 Halle)

Ab-initio exploration of Gd monolayer interfaced with WSe$_2$: from electronic and magnetic properties to the anomalous Hall effect
Heterostructures involving transition metal dichalcogenides (TMDs) have attracted significant research interest due to the richness and versatility of the underlying physical phenomena. In this work, we investigate a heterostructure consisting of a rare-earth material, specifically a Gd monolayer, interfaced with WSe$_2$. We explore its electronic structure, magnetic properties, and transport behavior, with particular emphasis on the emergence of the anomalous Hall effect (AHE). Both Gd and W a…

DLLMQuant: Quantizing Diffusion-based Large Language Models
Chen Xu, Dawei Yang
https://arxiv.org/abs/2508.14090 https://arxiv.org/pdf/2508.14090

DLLMQuant: Quantizing Diffusion-based Large Language Models
Diffusion-based large language models (DLLMs) have shown promise for non-autoregressive text generation, but their deployment is constrained by large model sizes and heavy computational costs. Post-training quantization (PTQ), a widely used method for compressing and accelerating Large Language Models (LLMs), suffers from severe accuracy degradation and reduced generalization performance when directly applied to DLLMs (e.g., AWQ suffers a 16% accuracy drop on LLADA under W4A4). This paper explo…

Image-Conditioned 3D Gaussian Splat Quantization
Xinshuang Liu, Runfa Blark Li, Keito Suzuki, Truong Nguyen
https://arxiv.org/abs/2508.15372 https://arxiv.…

Image-Conditioned 3D Gaussian Splat Quantization
3D Gaussian Splatting (3DGS) has attracted considerable attention for enabling high-quality real-time rendering. Although 3DGS compression methods have been proposed for deployment on storage-constrained devices, two limitations hinder archival use: (1) they compress medium-scale scenes only to the megabyte range, which remains impractical for large-scale scenes or extensive scene collections; and (2) they lack mechanisms to accommodate scene changes after long-term archival. To address these l…

Thermodynamics of the Reissner-Nordstr\"om black hole with quintessence matter on the EGUP framework
Hao Chen, Bekir Can L\"utf\"uo\u{g}lu, Hassan Hassanabadi, Zheng-Wen Long
https://arxiv.org/abs/2508.15467

Thermodynamics of the Reissner-Nordström black hole with quintessence matter on the EGUP framework
In this paper, we investigate the quantum correction on thermodynamics of the Reissner-Nordström black hole in the presence of the quintessence matter associated with dark energy. To this end, the modified Hawking temperature, heat capacity, and entropy functions of the black hole are derived. { Investigation reveals that the modified uncertainty principles and normalization factor $α$ restrict the lower bound value of horizon radius to affect the Hawking temperature and the parameter $η_{0}…

Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization
Yun Tang, Cindy Tseng
https://arxiv.org/abs/2509.15579 https://arxiv.org/pd…

Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization
Low latency speech human-machine communication is becoming increasingly necessary as speech technology advances quickly in the last decade. One of the primary factors behind the advancement of speech technology is self-supervised learning. Most self-supervised learning algorithms are designed with full utterance assumption and compromises have to made if partial utterances are presented, which are common in the streaming applications. In this work, we propose a chunk based self-supervised learn…